Cite
Notes
Only stored in your browser.
Attribution
RILQ: Rank-Insensitive LoRA-based Quantization Error Compensation for Boosting 2-bit Large Language Model Accuracy
arXiv 2024
Token-Scaled Logit Distillation for Ternary Weight Generative Language Models
token-scaled-logit-distillation-for-ternary
from 2 papers
Du-Seong Chang
Jungwook Choi
Minsoo Kim
Sukjin Hong
Euijai Ahn
Geonho Lee
Sihwa Lee
Wonyong Sung